Spatial relationship between objects in an image can help to gain a deep understanding of
the image. At present, spatial relationship recognition has received more and more …

Early action prediction aims to successfully predict the class label of an action before it is
completely performed. This is a challenging task because the beginning stages of different …

In the video-language domain, recent works in leveraging zero-shot Large Language Model-
based reasoning for video understanding have become competitive challengers to previous …

Traffic accident prediction in driving videos aims to provide an early warning of the accident
occurrence, and supports the decision making of safe driving systems. Previous works …

Early activity prediction/recognition aims to recognize action categories before they are fully
conveyed. Compared to full-length action sequences, partial video sequences only provide …

The leverage of large volumes of web videos paired with the query (short phrase for
searching the video) or surrounding text (long textual description, eg, video title) offers an …

Image-to-text tasks, such as open-ended image captioning and controllable image
description, have received extensive attention for decades. Here, we further advance this …

In this paper, we propose an ambiguousness-aware state evolution (AASE) method which
represents the uncertainty of the input sequence and evolves the subsequent skeletons to …

The precise recognition of entire classroom meta-actions is a crucial challenge for the
tailored adaptive interpretation of student behavior, given the intricacy of these actions. This …

Early action recognition (action prediction) from limited preliminary observations plays a
critical role for streaming vision systems that demand real-time inference, as video actions …